© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11373
    Prev
    Next
    INDEX
    Explanations

    the suffix "ani"

    oai_token-act-pair · gemini-2.0-flash

    ani

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ani
    -2.80
    ANI
    -2.19
    anis
    -1.13
    aniya
    -1.00
     ani
    -0.92
    ania
    -0.92
    anie
    -0.92
    anii
    -0.85
    hani
    -0.84
    <bos>
    -0.82
    POSITIVE LOGITS
    참고
    0.73
     defaultstate
    0.69
    initComponents
    0.66
     propOrder
    0.62
     ſche
    0.60
    ThemeOverlay
    0.60
     שוליים
    0.59
    diyesi
    0.59
    BufferException
    0.59
     useAppContext
    0.59
    Activations Density 0.753%

    No Known Activations