© 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. 5-CLT-HP
    7. 98050
    Prev
    Next
    INDEX
    Explanations

    the

    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
    ∮
    -0.40
    .
    -0.36
    伙
    -0.36
    Gent
    -0.36
    cshtml
    -0.35
    maß
    -0.35
    iální
    -0.35
     [*]
    -0.34
    prev
    -0.34
    prior
    -0.34
    POSITIVE LOGITS
     Administrativna
    0.84
    помним
    0.83
    mybatisplus
    0.82
    '):
    0.82
    Παραπομπές
    0.80
    "):
    0.77
    ]--;
    0.76
    `;
    0.76
    '){
    0.75
    tonode
    0.73
    Activations Density 0.030%

    No Known Activations