© 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. 1-CLT-HP
    7. 9775
    Prev
    Next
    INDEX
    Explanations

    alarm

    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
     Chwiliwch
    -0.76
     alarm
    -0.75
     alarms
    -0.71
     Alarm
    -0.71
     <<<<<<<<<<<<<<
    -0.66
    Autoritní
    -0.59
     للاسماء
    -0.58
    alarm
    -0.57
     ModelExpression
    -0.57
    Alarm
    -0.56
    POSITIVE LOGITS
    ArgsConstructor
    0.65
    WriteBarrier
    0.61
    igshid
    0.56
    "]);
    0.53
    Toponymie
    0.52
    Samedi
    0.52
    fetchone
    0.49
    <bos>
    0.49
    Awwww
    0.47
    ברס
    0.47
    Activations Density 0.134%

    No Known Activations