© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 533
    Prev
    Next
    INDEX
    Explanations

    various situations

    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
    __).
    -0.92
    .');
    -0.89
    ."));
    -0.87
    .
    -0.85
    .';
    -0.83
    .}}
    -0.82
    .";
    
    -0.80
    .")]
    -0.80
    .";
    -0.79
    .")
    
    -0.76
    POSITIVE LOGITS
     you
    0.64
    rupal
    0.53
     but
    0.52
     it
    0.48
     she
    0.47
     its
    0.44
     they
    0.44
     when
    0.43
     now
    0.43
     each
    0.42
    Activations Density 0.014%

    No Known Activations