© 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. 13958
    Prev
    Next
    INDEX
    Explanations

    problems

    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
    ThroughAttribute
    -0.60
    ]--;
    -0.56
    jstor
    -0.52
     ái
    -0.51
     te
    -0.49
    ist
    -0.47
     Hot
    -0.47
    vier
    -0.46
    tela
    -0.44
    ]++;
    -0.44
    POSITIVE LOGITS
     كومونز
    0.67
    Personendaten
    0.65
    WindowConstants
    0.60
     cortos
    0.59
    InvalidProtocol
    0.57
    CloseOperation
    0.56
    fjspx
    0.56
    parsedMessage
    0.56
     Escribe
    0.56
     större
    0.56
    Activations Density 0.384%

    No Known Activations