© 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. 0-CLT-HP
    7. 95085
    Prev
    Next
    INDEX
    Explanations

    alcohol investigations

    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
     investigating
    -0.84
     Investigating
    -0.72
     investigate
    -0.65
     investigates
    -0.63
     inexperienced
    -0.60
     daß
    -0.59
     ơn
    -0.58
    })));
    -0.54
     Inex
    -0.52
     experienced
    -0.52
    POSITIVE LOGITS
    دانشنامهٔ
    0.82
     Walkover
    0.68
    TagMode
    0.65
    Carriera
    0.60
    Ț
    0.58
    baomidou
    0.58
     colspan
    0.57
    bootstrapcdn
    0.56
    djangoproject
    0.55
    ExtendWith
    0.54
    Activations Density 0.228%

    No Known Activations