© 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. 1-CLT-HP
    7. 9521
    Prev
    Next
    INDEX
    Explanations

    solid

    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
     solid
    -0.94
    solid
    -0.91
    Solid
    -0.83
     SOLID
    -0.81
     Solid
    -0.75
    SOLID
    -0.73
     solids
    -0.72
     sólidos
    -0.58
     solides
    -0.57
     solide
    -0.56
    POSITIVE LOGITS
    ValueStyle
    0.75
    })()
    0.61
    __':
    0.60
     trajets
    0.60
    "]}
    0.58
    ']}
    0.56
    viating
    0.54
    Activité
    0.54
    ㅜ
    0.54
    "],
    0.53
    Activations Density 0.081%

    No Known Activations