© 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. 5122
    Prev
    Next
    INDEX
    Explanations

    Non-English

    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
    ement
    -0.51
     Betracht
    -0.49
    phen
    -0.46
    Referências
    -0.45
    vit
    -0.45
    manteau
    -0.45
    ಐ
    -0.45
    issan
    -0.44
    <bos>
    -0.44
     Khalid
    -0.44
    POSITIVE LOGITS
     linkovi
    0.69
    RTEE
    0.59
     ddelweddau
    0.59
    tahankan
    0.58
    SerializedName
    0.57
    niająca
    0.57
    новниш
    0.56
    pulumi
    0.56
     мәкал
    0.56
    OGND
    0.55
    Activations Density 0.001%

    No Known Activations