© 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. 0-CLT-HP
    7. 41391
    Prev
    Next
    INDEX
    Explanations

    Modification and feeling

    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
     stretching
    -0.99
     createSlice
    -0.63
    styleable
    -0.62
     Ulrich
    -0.58
     OkHttpClient
    -0.55
    tagHelperRunner
    -0.54
    OrBuilder
    -0.54
    rrggbb
    -0.53
     AttributeSet
    -0.53
     renovables
    -0.53
    POSITIVE LOGITS
    dieu
    0.66
     Vaj
    0.51
     CURIAM
    0.50
     purpoſe
    0.50
    KURZBESCHREIBUNG
    0.49
    eing
    0.49
    selle
    0.49
    rupa
    0.49
    DebuggerStep
    0.48
     firmas
    0.48
    Activations Density 0.057%

    No Known Activations