© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13907
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · 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
    DockStyle
    -0.66
     StringTokenizer
    -0.65
    pushFollow
    -0.63
     Meksiku
    -0.59
    AndEndTag
    -0.59
     Италијани
    -0.59
    ImageContext
    -0.59
    rrggbb
    -0.59
     ecosport
    -0.57
    WithEmail
    -0.57
    POSITIVE LOGITS
    :
    0.60
    下载附件
    0.48
     include
    0.48
    CompleteListener
    0.47
     assure
    0.45
    blest
    0.45
    )";
    0.44
    </sub>
    0.44
     be
    0.42
     WQS
    0.42
    Activations Density 0.006%

    No Known Activations