© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1109
    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
    strix
    -0.46
     Weyl
    -0.46
    gridy
    -0.45
     doré
    -0.45
    zzlies
    -0.44
    (&(
    -0.44
    maxx
    -0.43
     jadx
    -0.43
    ర
    -0.43
    arthed
    -0.42
    POSITIVE LOGITS
    BeginContext
    0.82
     szóci
    0.69
     &___
    0.67
    <%@
    0.66
     makeStyles
    0.66
    __(/*!
    0.65
    ]")]
    0.62
     Bioaccumulative
    0.61
     EnglishChoose
    0.60
     jLabel
    0.59
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.