© 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. 5-CLT-HP
    7. 4194
    Prev
    Next
    INDEX
    Explanations

    size and position

    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
     nahilalakip
    -0.85
    OUTSIDE
    -0.80
     Outside
    -0.76
     outside
    -0.73
    Outside
    -0.72
     OUTSIDE
    -0.71
    outside
    -0.70
     mergeFrom
    -0.68
     externi
    -0.67
     exterior
    -0.63
    POSITIVE LOGITS
     mCurrent
    0.60
    raszamy
    0.58
    raszam
    0.53
    hosa
    0.50
    ríamos
    0.46
    ]--;
    0.45
    guang
    0.45
     BorderRadius
    0.44
     getopt
    0.43
     onBackPressed
    0.41
    Activations Density 0.003%

    No Known Activations