© 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. 0-CLT-HP
    7. 43036
    Prev
    Next
    INDEX
    Explanations

    states

    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
     states
    -1.65
     States
    -1.48
     STATES
    -1.39
    States
    -1.27
    states
    -1.21
     estados
    -1.03
    STATES
    -0.96
     
    -0.85
     state
    -0.83
    ↵
    -0.81
    POSITIVE LOGITS
     ―――――
    1.45
     виправивши
    1.44
     myſelf
    1.39
     ་་
    1.36
     auffi
    1.35
    ^(@)
    1.35
     purpoſe
    1.35
     itſelf
    1.35
     doubtnut
    1.30
     tartalomajánló
    1.30
    Activations Density 0.310%

    No Known Activations