© 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. 20-CLT-HP
    7. 76516
    Prev
    Next
    INDEX
    Explanations

    Code or foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onItemClick
    -0.60
    setCharacter
    -0.53
    RunAsync
    -0.53
     Paral
    -0.53
    RetentionPolicy
    -0.47
    uku
    -0.47
    zA
    -0.45
     budget
    -0.45
    ]")]
    -0.44
    tock
    -0.44
    POSITIVE LOGITS
    GOTREF
    0.73
     kasarigan
    0.59
     dirait
    0.56
    <bos>
    0.54
     catég
    0.54
    طلحات
    0.53
    FieldDescriptor
    0.52
    XtraGrid
    0.52
    qtype
    0.51
    resar
    0.50
    Activations Density 0.005%

    No Known Activations