© 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. 5805
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     sī
    -0.46
    varargin
    -0.43
     دارد
    -0.43
     considérons
    -0.42
    InitStruct
    -0.42
    ngrx
    -0.41
    reducers
    -0.41
    — 
    -0.40
    はじめに
    -0.40
     xét
    -0.40
    POSITIVE LOGITS
    webElementGuid
    0.74
     &___
    0.73
     my
    0.73
    帖最后由
    0.70
     BoxFit
    0.70
     tartalomajánló
    0.69
    хьтан
    0.69
    mybatisplus
    0.69
     <=",
    0.68
    <bos>
    0.66
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.