© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 93587
    Prev
    Next
    INDEX
    Explanations

    starting early

    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
    AnchorStyles
    -0.75
    early
    -0.73
     تضيفلها
    -0.73
    يميديا
    -0.70
    enumii
    -0.70
    ValueStyle
    -0.69
     myö
    -0.69
     early
    -0.68
     définiti
    -0.68
     uncin
    -0.68
    POSITIVE LOGITS
     on
    0.50
     OFDb
    0.43
    ))){
    0.43
    ();}
    0.42
    stens
    0.42
    )];
    
    0.42
    }');
    0.40
     ON
    0.40
    .)}
    0.40
     bed
    0.40
    Activations Density 0.040%

    No Known Activations