© 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. 1-CLT-HP
    7. 15218
    Prev
    Next
    INDEX
    Explanations

    bib

    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
    ً
    -0.62
    <bos>
    -0.55
     bases
    -0.49
     Grand
    -0.44
     Lakes
    -0.44
     index
    -0.44
     base
    -0.41
     ActivatedRoute
    -0.41
     bib
    -0.40
     Librarians
    -0.40
    POSITIVE LOGITS
     незавершена
    0.93
    AndEndTag
    0.76
    MessageOf
    0.73
    发表于
    0.73
    yntaxException
    0.69
    ftagPool
    0.69
    copg
    0.65
    djangoproject
    0.64
    labelledby
    0.62
    脚注の使い方
    0.60
    Activations Density 0.016%

    No Known Activations