© 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. 92130
    Prev
    Next
    INDEX
    Explanations

    -

    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
    __))
    -0.73
     насељу
    -0.70
    ]")]
    -0.65
     snippetHide
    -0.62
    versy
    -0.61
    Попис
    -0.61
    SerializedName
    -0.60
     مشين
    -0.59
    ragment
    -0.59
    teness
    -0.59
    POSITIVE LOGITS
    /
    0.75
    ämpfer
    0.48
     vaccine
    0.48
    bor
    0.46
    Mal
    0.46
    fjspx
    0.46
     Mal
    0.46
     infected
    0.44
     /
    0.43
     Service
    0.42
    Activations Density 0.002%

    No Known Activations