© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 5285
    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
    ↵
    -0.64
     is
    -0.57
    .
    -0.55
    '
    -0.49
    <eos>
    -0.49
     will
    -0.48
     that
    -0.46
     of
    -0.44
     would
    -0.44
    ’
    -0.43
    POSITIVE LOGITS
    RenderAtEndOf
    1.32
    )";
    
    1.22
    Personendaten
    1.16
    "):
    
    1.16
     defaultstate
    1.14
    tvguidetime
    1.14
    !")
    
    1.13
    .)}
    1.13
    providedIn
    1.10
    LookAnd
    1.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.